EMGSense: A Low-Effort Self-Supervised Domain Adaptation Framework for EMG Sensing

Di Duan, Huanqi Yang, Guohao Lan, Tianxing Li, Xiaohua Jia, Weitao Xu*

*Corresponding author for this work

Research output: Chapter in Book/Conference proceedings/Edited volumeConference contributionScientificpeer-review

2 Citations (Scopus)
108 Downloads (Pure)

Abstract

This paper presents EMGSense, a low-effort self-supervised domain adaptation framework for sensing applications based on Electromyography (EMG). EMGSense addresses one of the fundamental challenges in EMG cross-user sensing—the significant performance degradation caused by time-varying biological heterogeneity—in a low-effort (data-efficient and label-free) manner. To alleviate the burden of data collection and avoid labor-intensive data annotation, we propose two EMG-specific data augmentation methods to simulate the EMG signals generated in various conditions and scope the exploration in label-free scenarios. We model combating biological heterogeneity-caused performance degradation as a multi-source domain adaptation problem that can learn from the diversity among source users to eliminate EMG heterogeneous biological features. To relearn the target-user-specific biological features from the unlabeled data, we integrate advanced self-supervised techniques into a carefully designed deep neural network (DNN) structure. The DNN structure can seamlessly perform two training stages that complement each other to adapt to a new user with satisfactory performance. Comprehensive evaluations on two sizable datasets collected from 13 participants indicate that EMGSense achieves an average accuracy of 91.9% and 81.2% in gesture recognition and activity recognition, respectively. EMGSense outperforms the state-of-the-art EMG-oriented domain adaptation approaches by 12.5%-17.4% and achieves a comparable performance with the one trained in a supervised learning manner.
Original languageEnglish
Title of host publicationProceedings of the 2023 IEEE International Conference on Pervasive Computing and Communications (PerCom)
Place of PublicationDanvers
PublisherIEEE
Pages160-170
Number of pages11
ISBN (Electronic)978-1-6654-5378-3
ISBN (Print)978-1-6654-5379-0
DOIs
Publication statusPublished - 2023
Event2023 IEEE International Conference on Pervasive Computing and Communications (PerCom) - Atlanta, United States
Duration: 13 Mar 202317 Mar 2023

Publication series

Name2023 IEEE International Conference on Pervasive Computing and Communications, PerCom 2023

Conference

Conference2023 IEEE International Conference on Pervasive Computing and Communications (PerCom)
Country/TerritoryUnited States
CityAtlanta
Period13/03/2317/03/23

Bibliographical note

Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care
Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.

Keywords

  • EMG sensing
  • biological heterogeneity
  • domain adaptation
  • self-supervised learning

Fingerprint

Dive into the research topics of 'EMGSense: A Low-Effort Self-Supervised Domain Adaptation Framework for EMG Sensing'. Together they form a unique fingerprint.

Cite this